Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to improvement and the concept of 'good' versus 'bad'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    better and good

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.43
     kew
    -0.40
    iconque
    -0.36
     asli
    -0.36
     tü
    -0.36
     Japan
    -0.34
    🦺
    -0.34
     keres
    -0.33
     propi
    -0.33
    __':
    -0.33
    POSITIVE LOGITS
    ftagPool
    0.67
     betterment
    0.60
    MLLoader
    0.59
    PerformLayout
    0.56
    UnusedPrivate
    0.54
    htaccess
    0.51
    awtextra
    0.49
    typeparam
    0.48
    wapV
    0.47
    webElementGuid
    0.47
    Act Density 0.014%

    No Known Activations